Model predictive control of an intensified continuous reactor using a neural network Wiener model

In this work a model predictive control approach based on a neural network Wiener model is developed and applied for an intensified continuous reactor. The Wiener model is constituted by two parts: a linear state space identified model based on nonlinear first-principle model, a nonlinear neural network model developed to predict the nonlinear controlled output. Next, a local linearization of neural network model at every sample instant is developed to guarantee an efficient online optimization. The performance of nonlinear controller is illustrated by simulations.